• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.97-108
• /
• 2022

The video-assisted human action recognition [1] field is one of the most active ones in computer vision research. Since the depth data [2] obtained by Kinect cameras has more benefits than traditional RGB data, research on human action detection has recently increased because of the Kinect camera. We conducted a systematic study of strategies for recognizing human activity based on deep data in this article. All methods are grouped into deep map tactics and skeleton tactics. A comparison of some of the more traditional strategies is also covered. We then examined the specifics of different depth behavior databases and provided a straightforward distinction between them. We address the advantages and disadvantages of depth and skeleton-based techniques in this discussion.

• 한국건축시공학회지
• /
• 제23권4호
• /
• pp.417-428
• /
• 2023

사고 원인에 대한 철저한 분석은 사고 재발 방지를 위한 필수적인 과정이다. 해체공사 사고의 원인을 살펴보면 작업자의 불안전한 행동, 불안전한 상태, 심리적·신체적 상태, 현장관리 원인 등 매우 다양하다. 현재 해체공사 사고통계는 지속적으로 조사·보고되고 있으나 사고 유형에 따른 보다 근본적인 원인 분류 정보가 필요하다. 본 연구에서는 하인리히의 도미노 이론을 바탕으로 해체공사 사고의 유형에 따라 사고원인(불안전한 행동, 불안전한 조건)과 휴먼에러(인적요인)를 분류하였다. 본 연구에서는 해체공사시 사고유형에 따라 사고원인을 체계적으로 분류하기 위해 QFD-FMEA(Quality Function Deployment - Failure Mode Effect Analysis) 3단계 모델을 사용하였다. 사고원인 분류 결과는 사고예방을 위한 안전지식 및 체크리스트로 활용할 수 있다.

• 농촌계획
• /
• 제5권1호
• /
• pp.56-65
• /
• 1999

The purpose of this study was to identify remained real state of the village groves in human settlement circle. That was practiced in case of Chinan-Gun region which traditional elements had well been conserved. 33 village groves were found by site survey, reference and interview in Chinan-Gun region. 31 of 51 village groves were clarified as complementing village grove by classification of grove character. It was identified through survey that many were partially destructed by development and human overuse. The results of this study showed general, socio-behavioral characteristics, characteristics of forest state and vegetation structure of village groves in Chinan-Gun region. Length, area, form, type, motive, location, relationship of those were analyzed to identify general characteristics. Facilities, human behavior and ownership of those were analyzed to identify socio-behavioral characteristics. Principal dominant species and appearing rate, height, width, density of those, species diversity of groves were analyzed to identify forest state and vegetation structure. Interrelation between each factor were analyzed and comparative review with previous studies was achieved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권6호
• /
• pp.1194-1208
• /
• 2010

As visual surveillance systems gain wider usage in a variety of fields, it is important that they are capable of interpreting scenes automatically, also known as "human motion analysis" (HMA). However, existing HMA methods are too domain specific and computationally expensive. This paper proposes a general purpose HMA method that is based on the idea that human beings tend to exhibit erratic motion patterns during abnormal situations. Limb movements are characterized using the statistics of angular and linear displacements. In addition, the method is enhanced via the use of the entropy of the Fourier spectrum to measure the randomness of subject's motions. Various experiments have been conducted and the results indicate that the proposed method has very high classification accuracy in identifying anomalous behavior.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제9권11호
• /
• pp.1133-1144
• /
• 2019

최근 스마트 기기의 발전으로 인터넷상에 존재하는 이미지 데이터의 양이 급속하게 증가하는 상황에서 효과적인 이미지 검색을 위한 다양한 방법들이 연구되고 있다. 기존의 이미지 검색 방법들은 이미지에 존재하는 물체들을 단순하게 검출하여 각 물체들의 라벨 정보에 근거한 검색을 수행하기 때문에 사용자가 원하는 이미지와 검색 결과로 얻은 이미지 간에 의미적 차이인 시맨틱 갭(Semantic Gap)이 발생된다. 이미지 검색에서 발생하는 시맨틱 갭을 줄이기 위해, 본 논문에서는 딥러닝 기반의 다중 객체 분류 모듈과 사람의 행위를 분류하는 모듈을 연결하고, 이 모듈들에 행위 온톨로지를 결합하였다. 즉, 딥러닝과 행위 온톨로지의 결합을 기반으로 객체들 간의 연관성을 고려한 이미지 검색 시스템을 제안한다. 이미지에 포함된 동적인 행위를 고려하기 위해 Walking과 Running 데이터를 이용하여 실험한 결과를 분석하였다. 제안한 방법은 향후 이미지 검색 결과의 정확도를 높일 수 있는 영상의 자동 주석 생성 연구에 확장하여 적용할 수 있다.

• 한국주거학회논문집
• /
• 제20권1호
• /
• pp.59-70
• /
• 2009

The purpose of the study is to suggest the amount of space for each behavior according to the classification of behavior in the housing to plan the optimal floor space of the elderly housing. The method for calculating space for behavior begins with classifying behaviors, identifying them and then taking pictures of the model of elderly people who reproduce each behavior. Based on the pictures, body parts which are necessary for each behavior are assembled and the formula for behavioral space is created. The space for behavior is produced considering the body dimensions of Korean elderly in their sixty's as well as the furniture size and the psychological distance between people. 3D modeling is used to verify the result. Human behaviors can be classified into individual-related, housework-related, family-related, reception-related and other behaviors. These five behaviors are subdivided into more specific behaviors. The area for each specific behavior is calculated with the anthropometric data of the elderly, preferred furniture dimension and psychological area. As a result the required area for specific behaviors is as follows: the behavior of sleeping in a bed needs $4.3m^2$; the behavior of changing clothes on a chair, $1.7m^2$; the behavior of watching TV on the floor $1.3m^2$, the behavior of working and reading using a desk, $2.1m^2$, the behavior of exercise, $2.5m^2$; the behavior of showering on a chair, $1.3m^2$ and showering using a wheelchair, $1.9m^2$; the behavior of toileting using a wheelchair, $2.3m^2$; the behavior of washing up using a wheelchair, $1.9m^2$; the behavior of eating using a table for four persons, $4.4m^2$; the behavior of cooking and washing dishes, $0.9m^2$ per counter-top; the behavior of washing clothes using a washing machine, $0.9m^2$; the behavior of ironing on the floor $1.4m^2$; the behavior of reception(three persons) on the floor considering personal space, $4.0m^2$; the behavior of taking on and off shoes on a chair, $1.3m^2$. The result of the study is utilized as quantitative data to calculate optimal floor space for elderly housing. In addition, qualitative data such as characteristics of housing preference, spacial usage and storage capacity are necessary to produce the floor space which can provide convenient and safe living environment.

• 스마트미디어저널
• /
• 제12권7호
• /
• pp.59-67
• /
• 2023

최근 인간의 자세와 행동을 추적하는 행동 분석 연구가 활발해지고 있다. 특히 2017년 CMU에서 개발한 오픈소스인 오픈포즈(OpenPose)는 사람의 외모와 행동을 추정하는 대표적인 방법이다. 오픈포즈는 사람의 키, 얼굴, 손 등의 신체부위를 실시간으로 감지하고 추정할 수 있어 스마트 헬스케어, 운 동 트레이닝, 보안시스템, 의료 등 다양한 분야에 적용될 수 있다. 본 논문에서는 헬스장에서 사용자들이 가장 많이 운동하는 Squat, Walk, Wave, Fall-down 4개 동작을 오픈포즈기반 딥러닝인 DNN과 CNN을 이용하여 운동 동작 분류 방법을 제안한다. 학습데이터는 녹화영상 및 실시간으로 카메라를 통해 사용자의 동작을 캡처해서 데이터 셋을 수집한다. 수집된 데이터 셋은 OpenPose을 이용하여 전처리과정을 진행하고, 전처리과정이 완료된 데이터 셋은 본 논문에서 제안한 DNN 및 CNN 모델 이용하여 운동 동작 분류를 학습한다. 제안한 모델에 대한 성능 오차는 MSE, RMSE, MAE를 사용한다. 성능 평가 결과, 제안한 DNN 모델 성능이 제안한 CNN 모델보다 우수한 것으로 나타났다.

• 혜화의학회지
• /
• 제12권2호
• /
• pp.85-103
• /
• 2004

From the studies on a few specific chapters of Tibetan Medical Painting, following conclusions were obtained. 1. The doctors of Tibet had to be not only academically and morally perfect, but he must show and have respect for his religion and his religous leaders and Gods. 2 The most main causes for all the disease that Tibetan Medicine resumed were hatred, delusion and ignorance of human mind which can make the physiological bile, wind, and phlegm to turn into pathological ones. 3. There is the classification of primary cause, which would be the human mind mentioned above, and the secondary cause which include dietary, behavior, seasonal problems, etc. 4. The Tibetans thought the digestive power is very important in the improvement or degravation of the disease. 5. More chapters were held for explaining the disease of fever, its clssification, stages, and cures which can indirectly show that the Tibetans might have thought it was very serious and could be very harmful. 6. The treatments for all the kinds of disease not only include medication and external therapy but also dietary and behavior regulations.

• 한국생활과학회지
• /
• 제16권1호
• /
• pp.89-101
• /
• 2007

This study deals with classification of various approaches regarding consumer experience, core characteristics, and contribution of experiential marketing. This study classifies seven approaches regarding consumer experience into 4 broad views (1)experience as experiential brand concept, 2)experience as a behavior, 3)experience as a behavior focusing on an affect, 4)experience as a holistic experience. Each of these 4 views of experience as well as the seven approaches is further explained in details. Five core characteristics of experiential marketing are suggested: l)forming a deep relationship between a customer and a brand, 2)being related to personal final values, 3)holistic experience with a brand, 4)fun, pleasure, and immersion, and 5)keeping customers through customer satisfaction and giving impression to a customer. Five propositions based on these core characteristics are suggested. The contribution of experiential marketing is suggested.

• 해양환경안전학회:학술대회논문집
• /
• 해양환경안전학회 2006년도 추계학술발표회
• /
• pp.283-289
• /
• 2006

이 연구에서는 국제적으로 관심이 집중되고 있는 FSA를 선박의 화재 안전 분야에 도입하기 위한 준비과정으로 화재안전도의 가장 중요한 지표인 사망확률의 근거가 되는 피난계산을 실습선의 모의훈련에 의해 계산하여 피난시간의 계산 및 성능기준 화재의 안전설계를 검토하였다. 그 결과 승선인원과 대피 통로의 폭과는 일정한 상관관계가 있으며 최적의 폭을 산정할 수 있음을 보였다. 그러나 선박 내부의 좁은 통로와 선박의 종류에 따른 특수한 구조를 고려할 때 일괄적인 적용은 어렵다. 또한 대피시간을 모의실험에 의해 추정하고 유출계수를 구한 결과 공용실의 유출계수와 비교하여 기관실의 인명위험성이 약 4배이상 높게 나타났다.